© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    5. GPT2-Small
    7. Residual Stream
    9. 6-RES-JB
    11. 23754
    Prev
    Next
    INDEX
    Explanations

    phrases related to legal or criminal actions and consequences

    oai_token-act-pair · gpt-3.5-turbo

    sentence-ending punctuation, suggesting a focus on the conclusion of statements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 6-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.hook_resid_pre
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    24,576
    Data Type
    torch.float32
    Hook Point
    blocks.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    cius
    -0.77
    agar
    -0.75
    boro
    -0.73
    erville
    -0.68
     proced
    -0.63
     Rebell
    -0.62
    ocial
    -0.61
     ¯
    -0.60
     Alphabet
    -0.60
     Quit
    -0.60
    POSITIVE LOGITS
    Among
    0.74
    Yesterday
    0.73
    Actor
    0.73
    Asked
    0.73
    Specifically
    0.72
    NPR
    0.72
    Eight
    0.72
    WHO
    0.71
    Earlier
    0.71
    Exc
    0.71
    Activations Density 0.279%

    No Known Activations